Qualcomm msmnile_gvmq for arm64
Geekbench ML Score
501
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | December 23 2024 03:18 AM |
| Views | 4 |
System Information
| System Information | |
|---|---|
| Operating System | Android 14 |
| Model | Qualcomm msmnile_gvmq for arm64 |
| Model ID | Qualcomm msmnile_gvmq for arm64 |
| Motherboard | msmnile |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 0 part 3403 revision 0 |
| Base Frequency | 2.59 GHz |
| Cluster 1 | 4 Cores @ 2.25 GHz |
| Cluster 2 | 4 Cores @ 2.59 GHz |
| Memory Information | |
|---|---|
| Size | 10.20 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | NNAPI |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
433
46.4 IPS |
|
|
Image Classification (F16)
|
100% |
420
45.0 IPS |
|
|
Image Classification (I8)
|
81% |
343
36.8 IPS |
|
|
Image Segmentation (F32)
|
100% |
704
4.35 IPS |
|
|
Image Segmentation (F16)
|
100% |
706
4.36 IPS |
|
|
Image Segmentation (I8)
|
89% |
642
3.96 IPS |
|
|
Pose Estimation (F32)
|
100% |
363
1.47 IPS |
|
|
Pose Estimation (F16)
|
100% |
359
1.45 IPS |
|
|
Pose Estimation (I8)
|
80% |
112
0.45 IPS |
|
|
Object Detection (F32)
|
100% |
487
17.1 IPS |
|
|
Object Detection (F16)
|
100% |
472
16.6 IPS |
|
|
Object Detection (I8)
|
52% |
392
13.8 IPS |
|
|
Face Detection (F32)
|
100% |
658
7.56 IPS |
|
|
Face Detection (F16)
|
100% |
660
7.58 IPS |
|
|
Face Detection (I8)
|
75% |
475
5.45 IPS |
|
|
Text Classification (F32)
|
100% |
921
364.5 IPS |
|
|
Text Classification (F16)
|
100% |
919
363.6 IPS |
|
|
Machine Translation (F32)
|
100% |
672
103.5 IPS |
|
|
Machine Translation (F16)
|
100% |
660
101.7 IPS |
